HumRightsBench - Issue Identification (I1): leaderboard

Metric: Accuracy (%; x100 of the exact-set match rate on the first issue-identification multiple-choice question per sub-scenario: which failure or obligation violation is most clearly engaged; pilot HumRightsBench question set on right-to-water scenarios validated by human rights experts; each question asked with five seeds and shuffled answer order (Qwen 3.5-9B multiple-choice types over four), responses through each provider's structured-output interface, errored calls counted as incorrect). Source: arxiv.org. Saturation forecast: Around 2028. 4 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)54
2GPT-552
3Claude Opus 4.747.3
4Qwen 3.5 9B39.4

Interactive version: theaggregate.ai/benchmark?slug=humrightsbench-issue-identification-i1 · How It Works · Data refreshed daily, snapshot 2026-09-26.